Shadow Detection In Images Research Articles

SEAT-YOLO: A squeeze-excite and spatial attentive you only look once architecture for shadow detection

Recently, several deep learning-based architectures have been utilized for the recognition of shadow regions in images and videos with the aim of classification and segmentation of shadow instances. The present work aims towards solving the problem of shadow recognition as a detection and regression problem. To solve the problem of shadow detection in images and videos, we have developed SEAT-YOLO, a deep learning-based shadow detection architecture. The backbone network of the proposed architecture is based on convolution layers, squeeze-excite blocks, spatial attention module, and spatial pyramid pooling layer and the detection network utilizes YOLO detection heads. The proposed SEAT-YOLO architecture is trained and tested on the publicly available SBU shadow detection dataset. For shadow detection on the SBU dataset, it achieved a mAP value of 59.53 %. Furthermore, the proposed SEAT-YOLO is capable of detecting small shadow regions with high accuracy which is a challenge with most deep learning-based detection architectures. Moreover, the other advantage of the proposed SEAT-YOLO is its ability to detect multiple shadow regions in a single image by drawing precise bounding boxes for overlapping shadows. The proposed SEAT-YOLO architecture has high practical implications in driverless vehicles for detection of shadow regions and take effective driving decisions.

MRPFA-Net for Shadow Detection in Remote-Sensing Images

The presence of shadows in high-resolution (HR) remote-sensing images reduces object detection accuracy. To address this problem, in this paper, we proposed a deep neural network algorithm for shadow detection by using the AISD and SSAD remote-sensing shadow image datasets. To improve the ability to extract spatial information from feature maps, we developed a cross-spatial attention module that focuses on semantic information in the horizontal and vertical directions at each position point on the remote-sensing image. This module overcomes the limitations of existing technologies in accurately judging small areas and suspected shadow areas and in missing or incorrectly detected shadow areas. In addition, to improve the ability to extract shadow features and the accuracy of shadow detection in remote-sensing images, we developed a channel attention module that assigns more attention to channels that conform to the shadow color characteristics. The network architecture comprises an encoder – decoder structure, with ResNeXt50 used as the backbone for the encoder and a multi resolution parallel fusion (MRPF) designed for the decoder; cross-spatial and channel attention were incorporated into the decoder unit. Experimental results demonstrated the superior performance of the proposed algorithm, with an F1 score of 92.6% for the shadow category on the test set, thus, outperforming other algorithms and making the proposed method an effective solution for shadow detection in HR remote-sensing images.

Automatic shadow detection in high-resolution multispectral remote sensing images

Shadows in high-resolution remote sensing satellite images distort both apparent shapes hues leading to lost features and difficult object analysis when processing these images. This negatively affects image color correction, recognition, classification, and urban reconstruction uses for these images. Although many shadow detection methods have been developed, there are still cases of missing detection of small shadows and misclassification of blue, green, and dark areas. We propose a novel logarithmic normalized mixed property-based shadow index (LNMPSI) for shadow detection in high resolution images using analysis of multispectral characteristics to improve on existing methods. Using color images from WorldView-3 and Gaofen-1, our method outperforms existing methods in both quantitative and qualitative terms. With good visual results and average accuracy in excess of 91%, our method is feasible, stable, and effective in detecting shadow regions and further reduces false positives caused by the loss of small details and misclassification of difficult areas.

A novel single robot image shadow detection method based on convolutional block attention module and unsupervised learning network.

Shadow detection plays a very important role in image processing. Although many algorithms have been proposed in different environments, it is still a challenging task to detect shadows in natural scenes. In this paper, we propose a convolutional block attention module (CBAM) and unsupervised domain adaptation adversarial learning network for single image shadow detection. The new method mainly contains three steps. Firstly, in order to reduce the data deviation between the domains, the hierarchical domain adaptation strategy is adopted to calibrate the feature distribution from low level to high level between the source domain and the target domain. Secondly, in order to enhance the soft shadow detection ability of the model, the boundary adversarial branch is proposed to obtain structured shadow boundary. Meanwhile, a CBAM is added in the model to reduce the correlation between different semantic information. Thirdly, the entropy adversarial branch is combined to further suppress the high uncertainty at the boundary of the prediction results, and it obtains the smooth and accurate shadow boundary. Finally, we conduct abundant experiments on public datasets, the RMSE has the lowest values with 9.6 and BER with 6.6 on ISTD dataset, the results show that the proposed shadow detection method has better edge structure compared with the existing deep learning detection methods.

Retraction Note: Single image shadow detection and removal based on feature fusion and multiple dictionary learning

Retraction Note: Single image shadow detection and removal based on feature fusion and multiple dictionary learning

Post-Processing for Shadow Detection in Drone-Acquired Images Using U-NET

Shadows in drone images commonly appear in various shapes, sizes, and brightness levels, as the images capture a wide view of scenery under many conditions, such as varied flying height and weather. This property of drone images leads to a major problem when it comes to detecting shadow and causes the presence of noise in the predicted shadow mask. The purpose of this study is to improve shadow detection results by implementing post-processing methods related to automatic thresholding and binary mask refinement. The aim is to discuss how the selected automatic thresholding and two methods of binary mask refinement perform to increase the efficiency and accuracy of shadow detection. The selected automatic thresholding method is Otsu’s thresholding, and methods for binary mask refinement are morphological operation and dense CRF. The study shows that the proposed methods achieve an acceptable accuracy of 96.43%.

A Newly Developed Algorithm for Cloud Shadow Detection—TIP Method

The masking of cloud shadows in optical satellite imagery is an important step in automated processing chains. A new method (the TIP method) for cloud shadow detection in multi-spectral satellite images is presented and compared to current methods. The TIP method is based on the evaluation of thresholds, indices and projections. Most state-of-the-art methods solemnly rely on one of these evaluation steps or on a complex working mechanism. Instead, the new method incorporates three basic evaluation steps into one algorithm for easy and accurate cloud shadow detection. Furthermore the performance of the masking algorithms provided by the software packages ATCOR (“Atmospheric Correction”) and PACO (“Python-based Atmospheric Correction”) is compared with that of the newly implemented TIP method on a set of 20 Sentinel-2 scenes distributed over the globe, covering a wide variety of environments and climates. The algorithms incorporated in each piece of masking software use the class of cloud shadows, but they employ different rules and class-specific thresholds. Classification results are compared to the assessment of an expert human interpreter. The class assignment of the human interpreter is considered as reference or “truth”. The overall accuracies for the class cloud shadows of ATCOR and PACO (including TIP) for difference areas of the selected scenes are 70.4% and 76.6% respectively. The difference area encompasses the parts of the classification image where the classification maps disagree. User and producer accuracies for the class cloud shadow are strongly scene-dependent, typically varying between 45% and 95%. The experimental results show that the proposed TIP method based on thresholds, indices and projections can obtain improved cloud shadow detection performance.

Image Shadow Detection and Removal Based on Region Matching of Intelligent Computing.

Shadow detection and removal play an important role in the field of computer vision and pattern recognition. Shadow will cause some loss and interference to the information of moving objects, resulting in the performance degradation of subsequent computer vision tasks such as moving object detection or image segmentation. In this paper, each image is regarded as a small sample, and then a method based on material matching of intelligent computing between image regions is proposed to detect and remove image shadows. In shadow detection, the proposed method can be directly used for detection without training and ensures the consistency of similar regions to a certain extent. In shadow removal, the proposed method can minimize the influence of shadow removal operation on other features in the shadow region. The experiments on the benchmark dataset demonstrate that the proposed approach achieves a promising performance, and its improvement is more than 6% in comparison with several advanced shadow detection methods.

Combined and optimized 2-steps ratio map for shadow detection in aerial images

Combined and optimized 2-steps ratio map for shadow detection in aerial images

Single image shadow detection via uncertainty analysis and GCN-based refinement strategy

Learning-based shadow detection methods have achieved an impressive performance, while these works still struggle on complex scenes, especially ambiguous soft shadows. To tackle this issue, this work proposes an efficient shadow detection network (ESDNet) and then applies uncertainty analysis and graph convolutional networks for detection refinement. Specifically, we first aggregate global information from high-level features and harvest shadow details in low-level features for obtaining an initial prediction. Secondly, we analyze the uncertainty of our ESDNet for an input shadow image and then take its intensity, expectation, and entropy into account to formulate a semi-supervised graph learning problem. Finally, we solve this problem by training a graph convolution network to obtain the refined detection result for every training image. To evaluate our method, we conduct extensive experiments on several benchmark datasets, i.e., SBU, UCF, ISTD, and even on soft shadow scenes. Experimental results demonstrate that our strategy can improve shadow detection performance by suppressing the uncertainties of false positive and false negative regions, achieving state-of-the-art results.

A feed‐forward framework integrating saliency and geometry discrimination for shadow detection in SAR images

Shadow has been increasingly a kind of significant aid information for object extraction and scene interpretation in synthetic aperture radar images, which makes SAR shadow detection an important issue. In this paper, we propose a feed-forward framework integrating saliency and geometry discrimination for shadow detection in SAR images. We firstly develop a global contrast based shadow saliency model to extract suspected shadows. Considering that such suspected regions mostly contain some non-shadow areas, a discrimination strategy based on geometric relationships between objects and shadows is designed to remove falsely detected areas. Then the remaining regions become the final shadow detection results. Several experiments are carried out on images from two real datasets, Moving and Stationary Target Acquisition Recognition and MiniSAR, to evaluate the performance of our method. From the perspectives of three commonly used metrics, the proposed algorithm comprehensively outperforms two other classic methods, presenting reliable shadow detection ability. Moreover, the detection results of the two classic methods are significantly enhanced in controlling false alarms after the discrimination module is introduced. The results demonstrate that our algorithm is practically applicable to shadow detection in SAR images, and the discrimination strategy can be flexibly extended for related tasks.

An Approach for Shadow Detection in Aerial Images Based on Multi-Channel Statistics

Shadows are likely to cause flaws in color interpretation, loss of image information or deformation of objects; this is a relevant issue owing to the fact that with the development of unmanned aerial vehicles and satellite devices, object detection by aerial images has become an essential aim to research works. The main contribution of this article is the development of an algorithm that processes shadow detection by detaching the channels red, green, blue and an additional low saturation channel on individual masks; having created those masks, the task of shadow detection is accomplished by conducting a pixel-by-pixel basis with the aid of a decision tree and statistical descriptors extracted out of the image, where the low saturation channel information leads to improvements on shadow detection accuracy in regions that contain asphalt and concrete. Thus, experimental results show the good behavior of shadow detection algorithm in terms of accuracy, over-segmentation, and under-segmentation, in which the accuracy of obtained shadow detection approaches a 94%.

Shadow detection of the satellite images of earth using ratio image pixels

Shadows, in aerial and satellite high-resolution images of earth, are a common phenomenon. Shadow causes false-color image, loss of information in the image, and false image segmentation. This leads to incorrect outputs of many image processing applications. In this paper, we address the problem of shadow detection in aerial high-resolution images of earth. The paper presents a proposed method that can be valuable in comparing it with other existing methods. The proposed work exploits the impact of ratio image pixel values on the process of shadow detection. The ratio image is the mathematical division of hue over the intensity component in the invariant color model. We propose a method, design, and develop an algorithm. In the designed algorithm, the input RGB aerial image of the earth is transformed into the invariant color model hue, saturation, and value (HSV). It acquires the average intensity value of pixels of the input RGB image components. Then, the ratio image of Hue (H) over Value (V) is calculated. Afterward, a power function is applied to this ratio to modify it by increasing the difference between pixel values very effectively. Finally, a threshold is applied to the modified ratio image to classify pixels into shadow and nonshadow. The proposed power function helps the threshold to better classify pixels into shadow and nonshadow. It has been implemented and experimented extensively. A comparative study has also been made with existing methods in the literature. In comparing the proposed algorithm and some existing algorithms, the experimental results show that the proposed has the ability to detect shadows with satisfying accuracy.

Shadow detection in SAR images based on greyscale distribution, a saliency model, and geometrical matching

ABSTRACT Shadow information has been widely used in synthetic aperture radar interpretation, but corresponding shadow detection technology has not been given much attention in past studies. In this paper, we propose a hierarchical architecture based on greyscale distribution, a saliency model, and geometrical matching for shadow detection in SAR images. We find that the greyscale distribution of one Gaussian filtered image might contain a ‘distortion’ in its uphill part, which is the effect of shadow existence. Based on this distortion, a global threshold can be determined and then be used to segment candidate shadows. If there is no obvious distortion, a shadow saliency model is proposed as a substitute to extract such candidate areas. Usually, these candidate areas may contain some non-shadow components. According to the geometric relationships between shadow and object, we design a matching strategy to eliminate non-shadow parts from candidate regions. The remained areas are final shadow detection results. Experiments on two real datasets, Moving and Stationary Target Acquisition Recognition and MiniSAR, show that our method performs much better than two other published methods. The results demonstrate the effectiveness and feasibility of our proposed algorithm in practical SAR shadow detection tasks.

Image Shadow Detection and Removal in Autonomous Vehicle Based on Support Vector Machine

Image Shadow Detection and Removal in Autonomous Vehicle Based on Support Vector Machine

ВИДАЛЕННЯ ТІНЕЙ НА ЦИФРОВИХ КОСМІЧНИХ ЗНІМКАХ НА ОСНОВІ ВЕЙВЛЕТ-ПЕРЕТВОРЕННЯ

Розглянуто проблему ідентифікації та компенсації тіней на космічних знімках високого просторового розрізнення. У роботі використано знімки міської території, отримані супутником WorldView-3. Наявність тіней на знімках може привести до втрати корисної інформації і навіть помилок в роботі алгоритмів розпізнавання, виявлення, відстеження і класифікації об’єктів. Запропоновано новий алгоритм автоматичного виявлення та усунення тіней цифрових космічних знімків, що дозволяє відновити освітленість та підвищити якість цих знімків. Для цього використано перехід до кольорової метрики HSV, вейвлет-перетворення та контурну сегментацію. Порівняння кількісних показників, а також візуальні результати показали перевагу використання запропонованого алгоритму. Результати роботи можуть бути використані при подальшому розпізнаванні об’єктів та тематичній обробці космічних знімків.

SDRNet: An end-to-end shadow detection and removal network

Image shadow detection and removal can effectively recover image information lost in the image due to the existence of shadows, which helps improve the accuracy of object detection, segmentation and tracking. Thus, aiming at the problem of the scale of the shadow in the image, and the inconsistency of the shadowed area with the original non-shadowed area after the shadow is removed, the multi-scale and global feature (MSGF) is used in the proposed method, combined with the non-local network and dense dilated convolution pyramid pooling network. Besides, aiming at the problem of inaccurate detection of weak shadows and complicated shape shadows in existing methods, the direction feature (DF) module is adopted to enhance the features of the shadow areas, thereby improving shadow segmentation accuracy. Based on the above two methods, an end-to-end shadow detection and removal network SDRNet is proposed. SDRNet completes the task of sharing two feature heights in a unified network without adding additional calculations. Experimental results on the two public datasets ISDT and SBU demonstrate that the proposed method achieves more than 10% improvement in the BER index for shadow detection and the RMSE index for shadow removal, which proves that the proposed SDRNet based on the MSGF module and DF module can achieve the best results compared with other existing methods.

Shadow Detection and Removal Techniques in Aerial Images

One of the complicated tasks is to detect & remove Shadow from single images of aerial images. Significant research is being carried out on various techniques of shadow detection. Over past decades, many shadow identification & removal approaches have been applied. Shadows are optical effects that arise when a region in the scene occurs when the primary light. Shadows are all over around us, so there is no confusion by their appearance. In this paper we provide an overview of the different methods used in the aerial images to identify & eliminate shadows & also provide their comparative study.

Shadow Detection in Still Road Images Using Chrominance Properties of Shadows and Spectral Power Distribution of the Illumination.

A well-known challenge in vision-based driver assistance systems is cast shadows on the road, which makes fundamental tasks such as road and lane detections difficult. In as much as shadow detection relies on shadow features, in this paper, we propose a set of new chrominance properties of shadows based on the skylight and sunlight contributions to the road surface chromaticity. Six constraints on shadow and non-shadowed regions are derived from these properties. The chrominance properties and the associated constraints are used as shadow features in an effective shadow detection method intended to be integrated on an onboard road detection system where the identification of cast shadows on the road is a determinant stage. Onboard systems deal with still outdoor images; thus, the approach focuses on distinguishing shadow boundaries from material changes by considering two illumination sources: sky and sun. A non-shadowed road region is illuminated by both skylight and sunlight, whereas a shadowed one is illuminated by skylight only; thus, their chromaticity varies. The shadow edge detection strategy consists of the identification of image edges separating shadowed and non-shadowed road regions. The classification is achieved by verifying whether the pixel chrominance values of regions on both sides of the image edges satisfy the six constraints. Experiments on real traffic scenes demonstrated the effectiveness of our shadow detection system in detecting shadow edges on the road and material-change edges, outperforming previous shadow detection methods based on physical features, and showing the high potential of the new chrominance properties.

Shadow Elimination Algorithm Using Color and Texture Features.

Shadow detection and removal in real scene images are a significant problem for target detection. This work proposes an improved shadow detection and removal algorithm for urban video surveillance. First, the foreground is detected by background subtraction and the shadow is detected by HSV color space. Using local variance and OTSU method, we obtain the moving targets with texture features. According to the characteristics of shadow in HSV space and texture feature, the shadow is detected and removed to eliminate the shadow interference for the subsequent processing of moving targets. Finally, we embed our algorithm into C/S framework based on the HTML5 web socket protocol. Both the experimental and actual operation results show that the proposed algorithm is efficient and robust in target detection and shadow detection and removal under different scenes.